CN112800663A - Inverse design method of aero-engine compressor rotor blade based on neural network - Google Patents
Inverse design method of aero-engine compressor rotor blade based on neural network Download PDFInfo
- Publication number
- CN112800663A CN112800663A CN202110000466.1A CN202110000466A CN112800663A CN 112800663 A CN112800663 A CN 112800663A CN 202110000466 A CN202110000466 A CN 202110000466A CN 112800663 A CN112800663 A CN 112800663A
- Authority
- CN
- China
- Prior art keywords
- blade
- neural network
- rotor blade
- search
- design
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
- F04D—NON-POSITIVE-DISPLACEMENT PUMPS
- F04D29/00—Details, component parts, or accessories
- F04D29/26—Rotors specially for elastic fluids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/15—Vehicle, aircraft or watercraft design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/17—Mechanical parametric or variational design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Mathematical Analysis (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Mathematical Optimization (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Pure & Applied Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Computational Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Fluid Mechanics (AREA)
- Algebra (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Automation & Control Theory (AREA)
- Aviation & Aerospace Engineering (AREA)
- Mechanical Engineering (AREA)
- Structures Of Non-Positive Displacement Pumps (AREA)
Abstract
The invention belongs to the technical field of mechanical design, and particularly relates to a reverse design method of an aero-engine compressor rotor blade based on a neural network. The invention carries out inverse design on the distribution condition of the compressor rotor blade with the given isentropic Mach number, and the specific steps comprise: obtaining a blade database and a corresponding geometric parameter database by using a Hicks-Henne type function parameterization method; performing flow field simulation by using computational fluid dynamics to obtain a pneumatic parameter database corresponding to a blade database; training an artificial neural network by using an artificial neural network and taking a geometric parameter database as input; using the trained artificial neural network to predict the isentropic Mach number distribution of the deformed blade; and (3) applying a mode searching method to enable the isentropic Mach number distribution to approach the target distribution, and finally obtaining the rotor blade which accords with the target isentropic Mach number distribution. The method has important engineering significance for improving the design level of the aero-engine and perfecting the design system of the aero-engine.
Description
Technical Field
The invention belongs to the technical field of mechanical design, and particularly relates to a reverse design method of an aero-engine compressor rotor blade.
Background
The impeller machine is widely applied to various departments of national economy and various fields of social life at present, and plays an important role in national economy, national defense construction and social development. In the power industry, steam turbines, gas turbines, water turbines, wind turbines and the like are key components for converting other forms of energy into mechanical energy; in the aviation field, an aircraft engine serves as the heart of an aircraft and determines the performance of the whole aircraft to some extent; in the aerospace field, a fuel transfer pump is an essential important component of a rocket engine; in addition, in other industrial sectors, such as the fields of petroleum, chemical engineering, steel, low-temperature refrigeration engineering, mining and the like, various pumps, fans and gas compressors play an important role.
The compendium for long-term scientific and technical development in the state (2006-2020 and 2013-2030) lists "large passenger aircraft" and "gas turbines and engines" as one of the major specialties. Large passenger planes and engines are symbolic projects for building innovative countries, and are open symbolic projects reformed in new periods. In aeronautical power engineering, aircraft powered by aero gas turbine engines have had a history of nearly 70 years since the first flight in 1939. Over the 70 years, aeronautical gas turbine engines have been of extreme importance for military and national economic construction and are highly appreciated by major industrial countries, whose technological development is rather rapid.
The related technology of the aeroengine represents the forefront of the research field of impeller machinery, and the design of each part is developing towards the direction of high load, high efficiency and wide working condition so as to achieve the aims of reducing the number of stages/parts, reducing the size of the engine, and improving the thrust-weight ratio and the stability. The fan/compressor and the turbine are important parts of an aeroengine, the internal flow of the fan/compressor and the turbine is very complex, the fan/compressor and the turbine not only have obvious three-dimensional unsteady flow property, but also have the phenomena of boundary layer separation, secondary flow, shock wave, wake mixing and the like which are complicated and complicated, and the phenomena are mutually influenced, so that the flow loss is directly caused, and the aerodynamic performance of the engine is obviously influenced. The gas compressor has the advantages that the gas compressor has counter-pressure flow in a channel, the boundary layer is thick, separation is easy to occur, the development difficulty is relatively high, and particularly for a multi-stage high-pressure gas compressor, the high performance and the high stability are difficult to maintain in a wide rotating speed range. Therefore, it is now common practice to optimize or scale on the basis of existing blades, for example, the high pressure compressor of the us E3 engine undergoes four-pass optimization modifications to meet the design requirements of the core engine and the engine.
With the continuous improvement of the performance requirements of the engine, the traditional blade design method needs to be further developed, and the numerical optimization of the blade becomes an important link in the design process. The current pneumatic optimization design method suitable for engineering application mainly comprises two types: the method comprises the steps that firstly, a positive design method is adopted, a numerical optimization technology is combined with flow field calculation, namely, initial blades are parameterized properly, the value range of parameters is given, a plurality of samples are generated, then relevant objective functions such as efficiency, margin and the like are selected to calculate and optimize a large number of samples, the essence is that the experience of designers is replaced by a mathematical process, the optimization effect is determined by the selection of parameterized variables and the advancement of an algorithm, and generally consumed machine time is large; the other is a reverse design method, namely the shape of the blade is reversely solved by giving the pneumatic parameters of the surface of the blade or a flow channel, such as pressure distribution and the like, and the method is characterized in that the method has clear physical significance, a designer can control important pneumatic parameters according to physical rules and experience, optimization is directly carried out aiming at the purposes of reducing the loss of the blade profile, changing the intensity or position of shock waves and the like, the method is more directional, and the calculated amount is generally smaller than that of the forward design method.
Therefore, the aero-engine blade optimization design is developed by taking the aero-engine compressor rotor blade as a research object and based on an inverse design method, the design efficiency of the aero-engine blade can be improved, the design period is shortened, and the aero-engine blade optimization design method has important application value in the aero-engine blade design. In the long run, the development of a rapid and efficient blade pneumatic reverse design method has important engineering significance for improving the design level of the aeroengine in China and perfecting the design system of the aeroengine in China.
Disclosure of Invention
The invention aims to provide a reverse design method of an aero-engine compressor rotor blade, which has the advantages of short design period, high design efficiency and good design effect.
The invention provides a reverse design method of an aero-engine compressor rotor blade, which adopts an artificial neural network technology to perform reverse design on a design target, namely the compressor rotor blade, under the condition of given isentropic Mach number distribution, and comprises the following specific steps:
(1) parameterization method by using Hicks-Henne type function[1]Parameterizing blade profile section disturbance quantities at three blade heights of the three-dimensional rotor blade and combining with a Latin hypercube sampling method[2]Obtaining a blade database and a corresponding geometric parameter database;
here, the three blade heights refer to typical three blade height positions that can best reflect the basic shape of the blade, and generally, the three blade heights are respectively: 30% of leaf height, 50% of leaf height, 70% of leaf height;
(2) performing flow field simulation by using computational fluid mechanics; reynolds average NS equation (RANS) solver based on finite volume method[3]Calculating the flow field in the compressor; calculating to obtain the height of three bladesThe constant entropy Mach number distribution is carried out, so that a pneumatic parameter database corresponding to the blade database is obtained;
(3) training an artificial neural network by using an artificial neural network technology and taking a geometric parameter database as an input and outputting a pneumatic parameter database;
here, the artificial neural network employs a back propagation neural network[4]The neural network has 2 layers of hidden layers, and the number of nodes is 60 and 90 respectively; the number of nodes of the input layer is 21, and the number of nodes of the output layer is 75; each layer of network is a full connection layer, and the activation function is a ReLU function;
(4) using the trained artificial neural network to predict the isentropic Mach number distribution of the deformed blade; applying a mode searching method [5], taking a space where the geometric parameters of the blade are located as a searching space, taking a neural network predicted value as a pneumatic parameter corresponding to a searching point, and taking a loss function as a mean square error between the predicted isentropic Mach number distribution and a target isentropic Mach number; carrying out mode search from the original appearance; in the searching process, the shape of the rotor blade is continuously modified, so that the isentropic Mach number distribution of the rotor blade approaches to the target distribution, and finally the rotor blade which meets the target isentropic Mach number distribution is obtained.
The method has the beneficial effects that:
the method can reversely design the transonic speed axial flow compressor rotor blade with target aerodynamic performance without modifying a fluid control equation and a solver, the designed blade can improve the performance of the compressor, and the method can be applied to the optimization design of the aero-engine blade, thereby improving the design efficiency and shortening the design period; the method has important engineering significance for improving the design level of the aero-engine and perfecting the design system of the aero-engine.
Drawings
Fig. 1 shows a profile of the blade height of the blade bank 50.
FIG. 2 is a three-dimensional computational grid and a two-dimensional cross-sectional view of a flow field in a compressor.
FIG. 3 is a comparison of the isentropic Mach number distributions of the original, target and reverse designed blades. Wherein (a) is 30% of the leaf height, (b) is 50% of the leaf height, and (c) is 70% of the leaf height.
FIG. 4 is a comparison of original and reverse design blade compressor performance: is a total pressure ratio-mass flow curve.
FIG. 5 is a comparison of original and reverse design blade compressor performance: efficiency-mass flow curve.
Detailed Description
Step (1): parameterizing the disturbance quantity of the three-dimensional rotor blade, and establishing a blade database and a geometric parameter database.
The shape perturbation is applied to 3 blade profile sections at 30%, 50% and 70% of the blade height by using Hicks-Henne type function, and the variable of the shape is parameterized. 5 disturbances are arranged on the Suction Surface (SS) of the blade profile, 2 disturbances are arranged on the Pressure Surface (PS), and the disturbance positions and the disturbance ranges are shown in the table 1.
Determining that the number of disturbance parameters of the section of a single blade profile is 7 and the number of total disturbance parameters is 21. Performing parameter disturbance by using a Latin hypercube sampling technology to obtain a blade database and a corresponding geometric parameter database, wherein the section range of a blade profile in a blade is shown in figure 1;
TABLE 1 disturbance factor Range
Step (2), obtaining a pneumatic parameter database through flow field simulation
Numerical simulation is carried out on the flow field in the gas compressor corresponding to the blades in the rotor blade database by using a three-dimensional RANS solver based on finite volume, the computational grid is shown in figure 2, the total node number of the grid is 772313, and the height of the grid on the wall surface is 772313
m，
Less than 10. By numerical simulation, the isentropic Mach number distribution of 30%, 50% and 70% of the blade heights of the blade wall is obtained, 25 key information points are extracted from the isentropic Mach number distribution, and the total number of the aerodynamic parameters is 75.
Step (3), training the artificial neural network, and carrying out inverse design
First, an artificial neural network is trained using the geometric parameter database as input and the pneumatic parameter database as output. The neural network uses a backward propagation neural network, which has 2 hidden layers in total, and the number of nodes is 60 and 90 respectively. The number of input layer nodes is 21 and the number of output layer nodes is 75. All the networks are full connection layers, and the activation function is a ReLU function. The training set sample size was 2000 and the test set sample size was 400. The learning rate is 0.03, and Adam is selected by the optimization method.
And (4) replacing CFD calculation with the trained neural network, and predicting the isentropic Mach number distribution of the deformed blade. Pattern search is an optimization method that does not require gradients. The mode search method realizes an algorithm through two search modes, namely axial search and mode search. The axial search is performed in the coordinate direction. By the axial search, a new base point with a smaller objective function value and a direction in which the objective function value is lowered can be obtained. This direction is used as a search direction in the pattern search. In the invention, the geometry of the blade is taken as a search space, the neural network predicted value is taken as a pneumatic parameter corresponding to the search point, and the loss function is the mean square error between the predicted isentropic Mach number distribution and the target isentropic Mach number. And performing mode search from the original shape, wherein the shape of the rotor blade is continuously modified in the searching process, so that the isentropic Mach number distribution of the rotor blade approaches to the target distribution. The finally obtained blade shape is the inverse design result of the target isentropic Mach number distribution.
The reverse design is carried out by taking a Rotor blade of NACA rotator 37 as an initial blade. And making a reverse design target for weakening the blade back channel shock wave. Fig. 3 shows the comparison of the isentropic mach number distributions of the original and target design results, and it can be seen from the figure that the isentropic mach number distribution of the target and the inverse design result are highly consistent, thus proving the effectiveness of the method. Fig. 4 and 5 show the total pressure ratio curve and the efficiency curve of the compressor corresponding to the original blade and the reverse blade. Compared with the original method, the mass flow of the gas compressor corresponding to the blades of the reverse design result is improved, and the total pressure ratio and the efficiency are comprehensively improved. The peak efficiency increased from 0.8494 to 0.8641, a relative increase of 1.7%. The total pressure ratio at the efficiency peak increases from 2.049 to 2.119. The method can be used for the design work of the rotor blade of the compressor, and the performance of the compressor is effectively improved.
The method can effectively perform reverse design on the rotor blades of the compressor aiming at the distribution target of the isentropic Mach number. By applying the method to the actual compressor blade, the mass flow, the pressure ratio and the efficiency of the compressor can be effectively improved.
Reference to the literature
[1] Hicks R M, Henne P A. Wing design by numerical optimization[J]. Journal of Aircraft, 1978, 15(7): 407-412.
[2] Helton J C, Davis F J. Latin hypercube sampling and the propagation of uncertainty in analyses of complex systems[J]. Reliability Engineering & System Safety, 2003, 81(1): 23-69.
[3] Jameson A, Schmidt W, Turkel E. Numerical solution of the Euler equations by finite volume methods using Runge Kutta time stepping schemes[C]//14th fluid and plasma dynamics conference. 1981: 1259.
[4] Rumelhart D E, McClelland J L. On learning the past tenses of English verbs[J]. 1986.
[5] Torczon V. On the convergence of pattern search algorithms[J]. SIAM Journal on optimization, 1997, 7(1): 1-25.。
Claims (4)
1. A reverse design method for an aero-engine compressor rotor blade is characterized in that an artificial neural network technology is adopted, and reverse design is carried out on a design target, namely the compressor rotor blade, under the condition of constant entropy Mach number distribution, and the specific steps are as follows:
(1) parameterizing blade profile section disturbance quantities at three blade heights of the three-dimensional rotor blade by using a Hicks-Henne type function parameterization method, and combining a Latin hypercube sampling method to obtain a blade database and a corresponding geometric parameter database;
the three blade heights refer to typical three blade height positions which can best reflect the basic shape of the blade;
(2) performing flow field simulation by using computational fluid mechanics; calculating the flow field in the gas compressor by adopting a solver based on a Reynolds average NS equation; calculating to obtain the distribution of the isentropic Mach numbers at the three blade heights of the blade so as to obtain a pneumatic parameter database corresponding to the blade database;
(3) training an artificial neural network by taking a geometric parameter database as an input and outputting a pneumatic parameter database by using the artificial neural network;
the artificial neural network adopts a backward propagation neural network, the neural network has 2 hidden layers in total, and the number of nodes is 60 and 90 respectively; the number of nodes of the input layer is 21, and the number of nodes of the output layer is 75; each layer of network is a full connection layer, and the activation function is a ReLU function;
(4) using the trained artificial neural network to predict the isentropic Mach number distribution of the deformed blade; applying a mode search method, taking the space where the geometric parameters of the blades are located as a search space, taking the neural network predicted value as a pneumatic parameter corresponding to the search point, and taking a loss function as the mean square error between the predicted isentropic Mach number distribution and the target isentropic Mach number; carrying out mode search from the original appearance; in the searching process, the shape of the rotor blade is continuously modified, so that the isentropic Mach number distribution of the rotor blade approaches to the target distribution, and finally the rotor blade which meets the target isentropic Mach number distribution is obtained.
2. The reverse design method for an aircraft engine compressor rotor blade according to claim 1, wherein the three blade heights are respectively taken as: 30% at leaf height, 50% at leaf height, 70% at leaf height.
3. The method for the inverse design of a rotor blade of an aircraft engine compressor according to claim 2, characterized in that the amount of turbulence is parameterized, wherein 5 perturbations are arranged on the Suction Side (SS) of the airfoil, 2 perturbations are arranged on the Pressure Side (PS), and the locations and ranges of the perturbations are given in the following table;
4. the method for reverse designing an aircraft engine compressor rotor blade according to claim 2, wherein the pattern search comprises two search patterns: axial search and mode search; the axial search is carried out in the coordinate direction, and a new base point with a smaller objective function value and a direction for reducing the objective function value are obtained through the axial search; this direction is used as a search direction in the pattern search.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110000466.1A CN112800663A (en) | 2021-01-03 | 2021-01-03 | Inverse design method of aero-engine compressor rotor blade based on neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110000466.1A CN112800663A (en) | 2021-01-03 | 2021-01-03 | Inverse design method of aero-engine compressor rotor blade based on neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112800663A true CN112800663A (en) | 2021-05-14 |
Family
ID=75807570
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110000466.1A Pending CN112800663A (en) | 2021-01-03 | 2021-01-03 | Inverse design method of aero-engine compressor rotor blade based on neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112800663A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114154275A (en) * | 2022-02-10 | 2022-03-08 | 北京航空航天大学 | Low-pressure turbine blade profile pneumatic design method based on optimal load distribution model optimization |
| CN114611333A (en) * | 2022-05-10 | 2022-06-10 | 中国航发上海商用航空发动机制造有限责任公司 | Compressor efficiency evaluation method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003106298A (en) * | 2001-09-28 | 2003-04-09 | Hitachi Ltd | Method and system for designing turbo type fluid machinery |
| US7191161B1 (en) * | 2003-07-31 | 2007-03-13 | The United States Of America As Represented By The Administrator Of The National Aeronautics And Space Administration | Method for constructing composite response surfaces by combining neural networks with polynominal interpolation or estimation techniques |
| CN110008653A (en) * | 2019-02-26 | 2019-07-12 | 西北工业大学 | A kind of aviation centrifugal pump blade profile optimum design method |
| CN110555214A (en) * | 2018-05-30 | 2019-12-10 | 中国航发商用航空发动机有限责任公司 | compressor blade profile construction method and compressor blade |
| CN110580396A (en) * | 2019-09-17 | 2019-12-17 | 上海理工大学 | Three-dimensional inverse design method for mechanical blade of impeller |
-
2021
- 2021-01-03 CN CN202110000466.1A patent/CN112800663A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003106298A (en) * | 2001-09-28 | 2003-04-09 | Hitachi Ltd | Method and system for designing turbo type fluid machinery |
| US7191161B1 (en) * | 2003-07-31 | 2007-03-13 | The United States Of America As Represented By The Administrator Of The National Aeronautics And Space Administration | Method for constructing composite response surfaces by combining neural networks with polynominal interpolation or estimation techniques |
| CN110555214A (en) * | 2018-05-30 | 2019-12-10 | 中国航发商用航空发动机有限责任公司 | compressor blade profile construction method and compressor blade |
| CN110008653A (en) * | 2019-02-26 | 2019-07-12 | 西北工业大学 | A kind of aviation centrifugal pump blade profile optimum design method |
| CN110580396A (en) * | 2019-09-17 | 2019-12-17 | 上海理工大学 | Three-dimensional inverse design method for mechanical blade of impeller |
Non-Patent Citations (5)
| Title |
|---|
| BIOLLO, ROBERTO等: "Recent advances in transonic axial compressor aerodynamics", 《PROGRESS IN AEROSPACE SCIENCES》 * |
| HE, LIU等: "Three-dimensional aerodynamic optimization for axial-flow compressors based on the inverse design and the aerodynamic parameters", 《JOURNAL OF TURBOMACHINERY》 * |
| 刘俊: "基于代理模型的高效气动优化设计方法及应用", 《中国优秀博硕士学位论文全文数据库(博士) 工程科技Ⅱ辑》 * |
| 刘俊文等: "压气机叶片多目标优化设计及稳定裕度分析", 《航空计算技术》 * |
| 刘凌君等: "基于神经网络的翼型气动力计算和反设计方法", 《气体物理》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114154275A (en) * | 2022-02-10 | 2022-03-08 | 北京航空航天大学 | Low-pressure turbine blade profile pneumatic design method based on optimal load distribution model optimization |
| CN114611333A (en) * | 2022-05-10 | 2022-06-10 | 中国航发上海商用航空发动机制造有限责任公司 | Compressor efficiency evaluation method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ekradi et al. | Performance improvement of a transonic centrifugal compressor impeller with splitter blade by three-dimensional optimization | |
| Dorfner et al. | Axis-asymmetric profiled endwall design by using multiobjective optimisation linked with 3D RANS-flow-simulations | |
| Schnoes et al. | Design optimization of a multi-stage axial compressor using throughflow and a database of optimal airfoils | |
| Lejon et al. | Multidisciplinary design of a three stage high speed booster | |
| CN112800663A (en) | Inverse design method of aero-engine compressor rotor blade based on neural network | |
| Zhong et al. | A 3D shape design and optimization method for natural laminar flow nacelle | |
| John et al. | Alleviation of shock-wave effects on a highly loaded axial compressor through novel blade shaping | |
| Gao et al. | A robust blade design method based on non-intrusive polynomial chaos considering profile error | |
| Giugno et al. | Adjoint-based optimization of a modern jet-engine fan blade | |
| Lengyel-Kampmann et al. | Generalized optimization of counter-rotating and single-rotating fans | |
| Fei et al. | Application of new empirical models based on mathematical statistics in the through-flow analysis | |
| Li et al. | Development and application of a throughflow method for high-loaded axial flow compressors | |
| Falla | Numerical investigation of the flow in tandem compressor cascades | |
| Giesecke et al. | Optimization of high subsonic, high reynolds number axial compressor airfoil sections for increased operating range | |
| Zhang et al. | Aerodynamic Performance Improvement of a Highly Loaded Compressor Airfoil with Coanda Jet Flap | |
| Komarov et al. | OPTIMIZATION APPROAC H AND SOME RESULTS FOR 2D COMPRESSOR AIRFOIL | |
| Becker et al. | Multi-objective optimization in axial compressor design using a linked cfd-solver | |
| Menegozzo et al. | Axial Rotor Design under Clean and Distortion Conditions using Mean-Line and CFD Methods | |
| Ramamurthy et al. | Dual point redesign of an axial compressor airfoil using a viscous inverse design method | |
| Li et al. | Multiobjective optimization approach to turbomachinery blades design | |
| Elqussas et al. | Axial flow turbine aerodynamic shape design optimization | |
| Li et al. | An Aerodynamic Loss Model for Axial Turbine Design | |
| Rehman et al. | Non-Axisymmetric Endwall Profiling of a Stator Row in the Presence of the Rotor in a High Pressure Turbine | |
| Schlaps et al. | Multi-disciplinary optimisation of a compressor rotor subjected to ice impact | |
| Immery et al. | Design of the Compression System of a Geared Turbofan |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210514 |